Netmind Parse PDF MCP

🚀 NetMind ParsePro

NetMind ParsePro is a high - quality, stable, and cost - effective PDF parsing AI service built and customized by the NetMind team. It can convert PDF files from specified URLs into desired output formats such as JSON and Markdown. This service is fully ready to integrate with the MCP server for seamless docking with AI agents.

🚀 Quick Start

NetMind ParsePro is a powerful PDF parsing AI service that can convert PDF files from URLs into JSON or Markdown. It's well - prepared for integration with MCP servers and AI agents.

✨ Features

• Convert PDF files from specified URLs to JSON or Markdown.
• Ready for seamless integration with MCP servers.

📦 Installation

Require UV (Fast Python Package and Project Manager)

If UV is not installed yet:

# Use Homebrew on macOS
brew install uv

Or

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Environment Variables

You can obtain the API key from Netmind.

• NETMIND_API_TOKEN: Your Netmind API key

Installation in Cursor & Claude Desktop and Windsurf

Add this tool as an MCP server by editing the Cursor/Claude/Windsurf configuration file.

{
  "mcpServers": {
    "parse-pdf": {
      "env": {
        "NETMIND_API_TOKEN": "XXXXXXXXXXXXXXXXXXXX"
      },
      "command": "uvx",
      "args": [
        "netmind-parse-pdf-mcp"
      ]
    }
  }
}

Cursor

• On macOS: /Users/your-username/.cursor/mcp.json
• On Windows: C:\Users\your-username\.cursor\mcp.json

Claude

• On macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
• On Windows: %APPDATA%/Claude/claude_desktop_config.json%

Windsurf

• On macOS: /Users/your-username/.codeium/windsurf/mcp_config.json
• On Windows: C:\Users\your-username\.codeium\windsurf\mcp_config.json

💻 Usage Examples

Basic Usage

The parse_pdf tool can be used to parse a PDF file from a given URL and extract its content.

# Assume we have a function to call the parse_pdf tool
import requests

url = "https://example.com/sample.pdf"
format = "json"
api_url = "your_api_endpoint"
headers = {
    "NETMIND_API_TOKEN": "your_api_token"
}
data = {
    "url": url,
    "format": format
}

response = requests.post(api_url, headers=headers, json=data)
print(response.json())

📚 Documentation

Components

Tools

• parse_pdf: Parse a PDF file from a given URL and extract its content, returning it in JSON or Markdown format.
  • url: Required: A URL (string) pointing to a PDF file accessible via HTTP(S).
  • format: Output format requirement. Supported: "json", "markdown".
  • Returns the content in the specified format (a JSON dictionary or a Markdown string).